Fix command line for evaluating rot+kp PHC3 model on AMASS

[IsshikiHugh]

Hi @ZhengyiLuo ,

Thanks for your super cool project! However, I met a problem during inspecting the code, and I did some walkaround to make it works (at least for me). Hope them help!

This PR contains two changes:

1. Remove the tailing spaces in README.md. (Automatically done by my editor, I think it's beneficial overall, so I keep it.)
2. Two missing arguments for evaluating rot+kp PHC3 model on AMASS.

They are committed separately, you can check the second commit directly for the change that matters.

Here are some explanation about the modifications.

PHC/README.MD

Lines 234 to 235 in 846988d

	## rotation + keypoint model (100% - PHC+)
	python phc/run_hydra.py learning=im_mcp_big exp_name=phc_comp_3 env=env_im_getup_mcp robot=smpl_humanoid env.zero_out_far=False robot.real_weight_porpotion_boxes=False env.num_prim=3 env.motion_file=sample_data/amass_isaac_standing_upright_slim.pkl env.models=['output/HumanoidIm/phc_3/Humanoid.pth'] env.num_envs=1 headless=False im_eval=True

Unfolding this command line, we will have:

python phc/run_hydra.py \
    learning=im_mcp_big  \
    exp_name=phc_comp_3 \
    env=env_im_getup_mcp \
    robot=smpl_humanoid \
    env.zero_out_far=False robot.real_weight_porpotion_boxes=False \
    env.num_prim=3 \
    env.motion_file=sample_data/amass_isaac_standing_upright_slim.pkl \
    env.models=['output/HumanoidIm/phc_3/Humanoid.pth'] \
    env.num_envs=1  \
    headless=False \
    im_eval=True

But when I run this command, it just fails to give correct results. Each agent just fell to the ground and can't get up. Which acts like the command actually launches a training. Then I did some walkaround.

Compared to other evaluation command on AMASS, e.g.:

PHC/README.MD

Lines 238 to 239 in 846988d

	## Shape + rotation + keypoint model
	python phc/run_hydra.py learning=im_mcp exp_name=phc_shape_mcp_iccv epoch=-1 test=True env=env_im_getup_mcp robot=smpl_humanoid_shape robot.freeze_hand=True robot.box_body=False env.z_activation=relu env.motion_file=sample_data/amass_isaac_standing_upright_slim.pkl env.models=['output/HumanoidIm/phc_shape_pnn_iccv/Humanoid.pth'] env.num_envs=1 headless=False im_eval=True

  python phc/run_hydra.py \
      learning=im_mcp \
      exp_name=phc_shape_mcp_iccv \
+     epoch=-1 \
+     test=True \
      env=env_im_getup_mcp \
      robot=smpl_humanoid_shape \
      robot.freeze_hand=True \
      robot.box_body=False \
      env.z_activation=relu \
      env.motion_file=sample_data/amass_isaac_standing_upright_slim.pkl \
      env.models=['output/HumanoidIm/phc_shape_pnn_iccv/Humanoid.pth'] \
      env.num_envs=1 \
      headless=False \
      im_eval=True

I think the epoch=-1 and test=True are needed but are missing. After adding these two, the results seem correct for me.

---

Thank you very much!